Binocular vision depth feature and apparent feature-combined face living body detection method

Abstract

The present invention provides a binocular vision depth feature and apparent feature-combined face living body detection method. The method includes the following steps that: step 1, a binocular vision system is established; step 2, a face is detected through the binocular vision system, so that a plurality of key points can be obtained; step 3, a binocular vision depth feature and a classification score corresponding to the binocular vision depth feature are obtained; step 4, a complete face area is intercepted from a left image, the complete face area is normalized to a fixed size, and a local binary pattern (LBP) feature is extracted so as to be adopted as an apparent feature descriptor; step 5, a face living body detection score corresponding to a micro-texture feature is obtained; and step 6, the classification score corresponding to the binocular vision depth feature obtained in the step 3 and the face living body detection score corresponding to the micro-texture feature obtained in the step 5 are fused in a decision-making layer, so that whether an image to be detected is a live body can be judged. The binocular vision depth feature and apparent feature-combined face living body detection method of the invention has the advantages of simple algorithm, high operation speed, high precision and the like. With the method adopted, a new and reliable method can be provided for living body face detection.

Description

technical field [0001] The present invention relates to the technical fields of computer vision and machine learning, in particular to a human face detection method combining binocular vision depth features and appearance features. Background technique [0002] Face recognition has made important progress in the past ten years. As an effective biometric-based identity authentication scheme, its application range has gradually expanded and has been applied to various industries. At the same time, attacks on the face recognition system are also constantly appearing, and the security of the face recognition system has encountered great challenges due to the innovative attack methods. If it is not handled properly, it will cause huge losses. Among these attack methods, using photos or videos to deceive is the most common. Intruders may rotate, flip, bend, and shake face pictures in front of image acquisition devices to create a real-life effect similar to legitimate users to dec...

AI Technical Summary

Problems solved by technology

[0004] The limitation of the above schemes is that none of the three-dimensional structural features of the face are used. Only using two-dimensional features, it is difficult to achieve a satisfactory living body recognition effect. In addition, most of the current living body technologies require the cooperation of users, which restricts the ability to use them in actual scenarios. Applications

Images